© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13597
    Prev
    Next
    INDEX
    Explanations

    Milan, Alex Ferguson

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KEY
    0.52
     سلام
    0.52
     उद्ध
    0.51
    喀
    0.51
     colch
    0.50
     کول
    0.50
    ÂN
    0.50
    컬
    0.50
    OSE
    0.50
     Coles
    0.49
    POSITIVE LOGITS
    adayo
    0.56
     raiding
    0.56
     pě
    0.53
     zrobi
    0.52
    到处
    0.52
     घेतली
    0.51
     raided
    0.51
    chetti
    0.50
     foiled
    0.50
     endeav
    0.50
    Activations Density 0.000%

    No Known Activations